© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8529
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity or existence of reasons and needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.57
    Cair
    -0.53
    WindowConstants
    -0.52
    VAO
    -0.50
    Ђ
    -0.50
     Reigns
    -0.49
    CreateMap
    -0.47
    ="@+
    -0.47
    [@
    -0.46
    waitKey
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.68
     becauſe
    0.67
    #+#
    0.66
     Monfieur
    0.65
     utafitiHapana
    0.63
     Chwiliwch
    0.61
     iſt
    0.61
     StatelessWidget
    0.61
     stanovnika
    0.60
     vertes
    0.60
    Activations Density 0.325%

    No Known Activations